Related papers: Multi-Class Unlearning for Image Classification via Weight Filtering

Multi-Class Unlearning for Image Classification via Weight Filtering

URL: http://arxiv.org/abs/2304.02049v2
Date: Sat, 8 Jun 2024 10:56:27 GMT
Title: Multi-Class Unlearning for Image Classification via Weight Filtering
Authors: Samuele Poppi, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara,
Abstract summary: Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. We achieve this by modulating the network's components using memory matrices, enabling the network to demonstrate selective unlearning behavior for any class after training. We test the proposed framework on small- and medium-scale image classification datasets, with both convolution- and Transformer-based backbones.
Score: 44.707144011189335
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a single class, our framework unlearns all classes in a single round. We achieve this by modulating the network's components using memory matrices, enabling the network to demonstrate selective unlearning behavior for any class after training. By discovering weights that are specific to each class, our approach also recovers a representation of the classes which is explainable by design. We test the proposed framework on small- and medium-scale image classification datasets, with both convolution- and Transformer-based backbones, showcasing the potential for explainable solutions through unlearning.

Related papers

Knowledge Adaptation Network for Few-Shot Class-Incremental Learning [23.90555521006653]
Few-shot class-incremental learning aims to incrementally recognize new classes using a few samples. One of the effective methods to solve this challenge is to construct prototypical evolution classifiers. Because representations for new classes are weak and biased, we argue such a strategy is suboptimal.
arXiv Detail & Related papers (2024-09-18T07:51:38Z)
Experience feedback using Representation Learning for Few-Shot Object Detection on Aerial Images [2.8560476609689185]
The performance of our method is assessed on DOTA, a large-scale remote sensing images dataset. It highlights in particular some intrinsic weaknesses for the few-shot object detection task.
arXiv Detail & Related papers (2021-09-27T13:04:53Z)
Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer [112.95747173442754]
A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier. Most existing methods meta-learn all three model components for fast adaptation to a new class. In this work we propose to simplify the meta-learning task by focusing solely on the simplest component, the classifier.
arXiv Detail & Related papers (2021-08-06T10:20:08Z)
Rectifying the Shortcut Learning of Background: Shared Object Concentration for Few-Shot Image Recognition [101.59989523028264]
Few-Shot image classification aims to utilize pretrained knowledge learned from a large-scale dataset to tackle a series of downstream classification tasks. We propose COSOC, a novel Few-Shot Learning framework, to automatically figure out foreground objects at both pretraining and evaluation stage.
arXiv Detail & Related papers (2021-07-16T07:46:41Z)
Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Models [4.189643331553922]
We propose a deep invertible hybrid model which integrates discriminative and generative learning at a latent space level for semi-supervised few-shot classification. Our main originality lies in our integration of these components at a latent space level, which is effective in preventing overfitting.
arXiv Detail & Related papers (2021-05-22T05:55:16Z)
Attribute Propagation Network for Graph Zero-shot Learning [57.68486382473194]
We introduce the attribute propagation network (APNet), which is composed of 1) a graph propagation model generating attribute vector for each class and 2) a parameterized nearest neighbor (NN) classifier. APNet achieves either compelling performance or new state-of-the-art results in experiments with two zero-shot learning settings and five benchmark datasets.
arXiv Detail & Related papers (2020-09-24T16:53:40Z)
Meta Learning for Few-Shot One-class Classification [0.0]
We formulate the learning of meaningful features for one-class classification as a meta-learning problem. To learn these representations, we require only multiclass data from similar tasks. We validate our approach by adapting few-shot classification datasets to the few-shot one-class classification scenario.
arXiv Detail & Related papers (2020-09-11T11:35:28Z)
A Few-Shot Sequential Approach for Object Counting [63.82757025821265]
We introduce a class attention mechanism that sequentially attends to objects in the image and extracts their relevant features. The proposed technique is trained on point-level annotations and uses a novel loss function that disentangles class-dependent and class-agnostic aspects of the model. We present our results on a variety of object-counting/detection datasets, including FSOD and MS COCO.
arXiv Detail & Related papers (2020-07-03T18:23:39Z)
ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification [49.87503122462432]
We introduce a novel neural network termed Relation-and-Margin learning Network (ReMarNet) Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples.
arXiv Detail & Related papers (2020-06-27T13:50:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.